QwenTool Switching in Composer
Qwen composer: multimodal + menu (image, video, search, research, dev, slides); Qwen3.7-Plus picker; Auto/Thinking/Fast; Voice Chat vs dictation; Create Image with Qwen-Image and aspect controls.
Empty home with Ask Qwen, Auto effort, mic, and waveform button; Qwen3.7-Plus in header.
What's happening
Qwen keeps a calm chat shell and hides multimodal jobs in +. Effort (Auto/Thinking/Fast) sits on the bar; chat models sit in the header; image models sit inside Create Image. Voice Chat and dictation are separate controls.
Patterns
Create Image/Video, search, research, dev, and slides from one flyout
Qwen3.x chat models vs Qwen-Image engines with separate pickers
Dictation expands composer; Voice/Video Chat opens omni sessions
UX Insights
- •Multimodal catalog lives in +, not home pills
- •Three model names can show at once (chat, image, effort)
- •Voice personas are searchable with playful copy
- •Use Prompt on gallery cards teaches generation prompts
Design Decisions
Qwen splits text chat, image studio, and omni voice into one URL with nested mode chips instead of separate home surfaces.
More case studies
GLM (Z.ai)Tool Switching in Composer
GLM (Z.ai) composer: Magic Design, Full-Stack, and Write Code pills; Search vs Advanced Search; GLM-4.7 through 5.2; Deep Think Max; separate Agent home with Discord/Lark/WeChat.
KimiTool Switching in Composer
Kimi composer: agent pills that rewrite the bar into Websites, Docs, Sheets, Design, and Swarm; Instant/K3/K3 Swarm; + for files plugins skills and search; slash invoke.
ManusTask composer & modes
Manus assignment bar: connector suggestions, + attach menu, skills, cloud computer, agent tiers, voice input, and mode-specific flows like Slides.
ChatGPTTool Switching in Composer
ChatGPT allows users to select and activate different AI capabilities like Code Interpreter, DALL·E, and Web Search directly from the composer interface.